Bridging text and crystal structures: literature driven contrastive learning for materials science

Today's article comes from the journal of Machine Learning Science and Technology. The authors are Suzuki et al., from Toyota Motor Corporation, in Japan. In this paper they introduce CLaSP: Contrastive Language-Structure Pre-training. It's a system that learns to connect crystal structures with the words used to describe them in the scientific literature.

DOI: 10.1088/2632-2153/ade58c

Book
Book

Members Only

You must be an active Journal Club member to access this content. If you're already a member, click the blue button to login. If you're not a member yet, click the sign-up button to get started.

Login to My Account Sign Up